qdrant-hybrid-search-combining

# Combining Prefetch Results The outer query fuses ranked candidate lists from all parallel prefetches into one ranked list of results. Fusion methods differ in whether they use rank, score or directly vector representations of candidates (their similarity to the outer query) and whether final score incorporates payload metadata. All methods support flat (one fusion step) and nested (multi-stage) prefetch structures. ## Scores Are Not Comparable Across Prefetches & You Want Some Easy Baseline Use when: searches produce scores on different scales, like BM25 and cosine on dense embeddings. ### RRF - **[RRF](https://skills.qdrant.tech/md/documentation/search/hybrid-queries/?s=reciprocal-rank-fusion-rrf)** (Reciprocal Rank Fusion) — rank-based, ignores scores magnitude, a decent default to start with. - Tune `k` to [control rank sensitivity in RRF fusion](https://skills.qdrant.tech/md/documentation/search/hybrid-queries/?s=setting-rrf-constant-k). - Add per-prefetch **weights** when one search should dominate, using [Weighted RRF](https://skills.qdrant.tech/md/documentation/search/hybrid-queries/?s=weighted-rrf). Weights should be customized per collection and retrievers' score distributions! ### DBSF - **[DBSF](https://skills.qdrant.tech/md/documentation/search/hybrid-queries/?s=distribution-based-score-fusion-dbsf)** (Distribution-Based Score Fusion) — normalizes score distributions per prefetch before fusing them, for that, instead of min-max, uses mean +- 3 deviations on...